Thi Hong Nhan Vu and Yang Koo Lee and Namsrai Oyun-Erdene (2016) Activity Recognition based on Clustering Methods for Senior Homecare Services. In: The 9th International Conference on Frontiers of Information Technology, Applications and Tools, 31 March - 3 April 2016, Zhuhai, China.
Full text not available from this repository.
In modern society, most seniors prolong their independence. To guarantee the safety of them when living on their own, we need to monitor their activities all the time and react to critical situations. The rapid advances in wireless networks, wearable sensors, and communications technologies pave the way for the advent of homecare service systems. Activity recognition is a crucial task in building such systems. This paper investigates two clustering methods, kmeans and Self-organizing map (SOM) for recognizing human daily activities. An experiment is performed on a real data set. The results show that k-means performs pretty well in classifying two activities; however the accuracy is pretty low when the data set is scaled up to five activities. SOM outperforms k-means in most cases of data sets. On average, the resulting accuracy of SOM is 87% and of k-means is 54% for five activities. As a result, SOM is most suitable to be integrated in systems for providing remote homecare services.
|Item Type:||Conference or Workshop Item (Paper)|
|Subjects:||Information Technology (IT)|
|Divisions:||Faculty of Information Technology (FIT)|
|Deposited By:||VÅ© Thá»� H|
|Deposited On:||05 Dec 2016 03:18|
|Last Modified:||05 Dec 2016 03:18|
Repository Staff Only: item control page